audio-5

Bandwidth Extension

3260 papers • 126 benchmarks • 313 datasets

Bandwidth extension is the task of expanding the bandwidth of a signal in a way that approximates the original or desired higher bandwidth signal.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in bandwidth-extension-11

Trend

Dataset

Best Model

Actions

VCTK

Libraries

i

Use these libraries to find bandwidth-extension-11 models and implementations

Datasets

VCTK

Subtasks

No subtasks available.

Most implemented papers

On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks

Serkan Sulun, M. Davies•Fri Nov 13 2020

A data augmentation strategy is proposed which utilizes multiple low-pass filters during training and leads to improved generalization to unseen filtering conditions at test time, which results in a lower SNR than the band-limited input.

22

Content

0

Paper Graph

Super-Resolution with Deep Convolutional Sufficient Statistics

Joan Bruna, Yann LeCun, P. Sprechmann•Tue Nov 17 2015

This paper proposes to use as conditional model a Gibbs distribution, where its sufficient statistics are given by deep convolutional neural networks, and the features computed by the network are stable to local deformation, and have reduced variance when the input is a stationary texture.

337 0

Paper Graph

HIFI++: A Unified Framework for Bandwidth Extension and Speech Enhancement

D. Vetrov, Pavel Andreev, Aibek Alanov, Oleg Ivanov•Wed Mar 23 2022

It is shown that with the improved generator architecture, HiFi++ performs better or comparably with the state-of-the-art in these tasks while spending significantly less computational resources.

67 0

Paper Graph

Wavenet Based Low Rate Speech Coding

Quan Wang, Florian Stimberg, W. Kleijn, Felicia S. C. Lim, Alejandro Luebs, J. Skoglund, Thomas C. Walters•Thu Nov 30 2017

This work describes how a WaveNet generative speech model can be used to generate high quality speech from the bit stream of a standard parametric coder operating at 2.4 kb/s and shows that the speech produced by the system is able to additionally perform implicit bandwidth extension and does not significantly impair recognition of the original speaker for the human listener.

151 0

Paper Graph

Tunet: A Block-Online Bandwidth Extension Model Based On Transformers And Self-Supervised Pretraining

Viet-Anh Nguyen, Anh H. T. Nguyen, Andy W. H. Khong•Mon Oct 25 2021

A block-online variant of the temporal feature-wise linear modulation (TFiLM) model to achieve bandwidth extension that simplifies the UNet backbone of the TFiLM to reduce inference time and employs an efficient transformer at the bottleneck to alleviate performance degradation.

28 0

Paper Graph

Neural Vocoder is All You Need for Speech Super-resolution

Deliang Wang, Haohe Liu, Xubo Liu, Qiuqiang Kong, W. Choi, Qiao Tian•Sun Mar 27 2022

This paper proposes a neural vocoder based speech super-resolution method (NVSR) that can handle a variety of input resolution and upsampling ratios and demonstrates that prior knowledge in the pre-trained vocoder is crucial for speech SR by performing mel-bandwidth extension with a simple replication-padding method.

66 0

Paper Graph

EBEN: Extreme Bandwidth Extension Network Applied To Speech Signals Captured With Noise-Resilient Body-Conduction Microphones

Julien Hauret, Thomas Joubaud, V. Zimpfer, É. Bavu•Mon Oct 24 2022

Extreme Bandwidth Extension Network (EBEN), a Generative Adversarial network (GAN) that enhances audio measured with body-conduction microphones, can achieve state-of-the-art results with a lightweight generator and real-time compatible operation.

19 0

Paper Graph

BEHM-GAN: Bandwidth Extension of Historical Music Using Generative Adversarial Networks

Eloi Moliner, V. Välimäki•Tue Apr 12 2022

The results of a formal blind listening test show that BEHM-GAN significantly increases the perceptual sound quality in early-20th-century gramophone recordings and represents a relevant step toward data-driven music restoration in real-world scenarios.

25 0

Paper Graph

Solving Audio Inverse Problems with a Diffusion Model

J. Lehtinen, Eloi Moliner, V. Välimäki•Wed Oct 26 2022

The results show that CQT-Diff outperforms the compared baselines and ablations in audio bandwidth extension and, without retraining, delivers competitive performance against modern baselines in audio inpainting and declipping.

79 0

Paper Graph

Analysing Diffusion-based Generative Approaches Versus Discriminative Approaches for Speech Restoration

Julius Richter, Simon Welker, Jean-Marie Lemercier, Timo Gerkmann•Thu Nov 03 2022

The generative approach performs globally better than its discriminative counterpart on all tasks, with the strongest benefit for non-additive distortion models, like in dereverberation and bandwidth extension.

50 0

Paper Graph

Adding a benchmark result helps the community track progress.